---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
  results:
  - task:
      name: Audio Classification
      type: audio-classification
    dataset:
      name: GTZAN
      type: marsyas/gtzan
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8581829692940804
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# distilhubert-finetuned-gtzan

This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5627
- Accuracy: 0.8582

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step   | Validation Loss | Accuracy |
|:-------------:|:-----:|:------:|:---------------:|:--------:|
| 0.4173        | 1.0   | 7108   | 0.5416          | 0.8343   |
| 0.235         | 2.0   | 14216  | 0.4663          | 0.8251   |
| 0.1549        | 3.0   | 21324  | 0.5940          | 0.8325   |
| 0.2558        | 4.0   | 28432  | 0.6608          | 0.8531   |
| 0.2991        | 5.0   | 35540  | 0.9088          | 0.8305   |
| 0.4773        | 6.0   | 42648  | 0.9120          | 0.8390   |
| 0.5235        | 7.0   | 49756  | 0.9285          | 0.8455   |
| 0.0004        | 8.0   | 56864  | 1.0259          | 0.8492   |
| 0.1918        | 9.0   | 63972  | 1.2874          | 0.8411   |
| 0.0002        | 10.0  | 71080  | 1.1114          | 0.8476   |
| 0.0001        | 11.0  | 78188  | 1.4835          | 0.8393   |
| 0.0013        | 12.0  | 85296  | 1.3846          | 0.8541   |
| 0.0001        | 13.0  | 92404  | 1.3622          | 0.8507   |
| 0.0909        | 14.0  | 99512  | 1.4672          | 0.8487   |
| 0.0001        | 15.0  | 106620 | 1.4243          | 0.8571   |
| 0.0           | 16.0  | 113728 | 1.5627          | 0.8582   |
| 0.0           | 17.0  | 120836 | 1.8146          | 0.8531   |
| 0.0           | 18.0  | 127944 | 1.8596          | 0.8550   |
| 0.0           | 19.0  | 135052 | 1.9233          | 0.8574   |
| 0.0           | 20.0  | 142160 | 1.9875          | 0.8569   |


### Framework versions

- Transformers 4.39.3
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2